diff options
author | Ingo Molnar <mingo@elte.hu> | 2009-06-07 12:22:15 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2009-06-07 12:22:15 +0200 |
commit | 5f4457a4f62cc9d78e04c0eb12ff0540899aad89 (patch) | |
tree | 0b973d527ea6b2ae31e08da0746b4965a3c5a6d8 /fs/cifs/cifs_unicode.c | |
parent | 9b94b3a19b13e094c10f65f24bc358f6ffe4eacd (diff) | |
parent | b87297fb405ef13cac375f202d114323b076a56d (diff) |
Merge branch 'linus' into x86/cpu
Diffstat (limited to 'fs/cifs/cifs_unicode.c')
-rw-r--r-- | fs/cifs/cifs_unicode.c | 198 |
1 files changed, 181 insertions, 17 deletions
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 7d75272a6b3..60e3c4253de 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -1,7 +1,7 @@ /* * fs/cifs/cifs_unicode.c * - * Copyright (c) International Business Machines Corp., 2000,2005 + * Copyright (c) International Business Machines Corp., 2000,2009 * Modified by Steve French (sfrench@us.ibm.com) * * This program is free software; you can redistribute it and/or modify @@ -26,31 +26,157 @@ #include "cifs_debug.h" /* - * NAME: cifs_strfromUCS() - * - * FUNCTION: Convert little-endian unicode string to character string + * cifs_ucs2_bytes - how long will a string be after conversion? + * @ucs - pointer to input string + * @maxbytes - don't go past this many bytes of input string + * @codepage - destination codepage * + * Walk a ucs2le string and return the number of bytes that the string will + * be after being converted to the given charset, not including any null + * termination required. Don't walk past maxbytes in the source buffer. */ int -cifs_strfromUCS_le(char *to, const __le16 *from, - int len, const struct nls_table *codepage) +cifs_ucs2_bytes(const __le16 *from, int maxbytes, + const struct nls_table *codepage) { int i; - int outlen = 0; + int charlen, outlen = 0; + int maxwords = maxbytes / 2; + char tmp[NLS_MAX_CHARSET_SIZE]; - for (i = 0; (i < len) && from[i]; i++) { - int charlen; - /* 2.4.0 kernel or greater */ - charlen = - codepage->uni2char(le16_to_cpu(from[i]), &to[outlen], - NLS_MAX_CHARSET_SIZE); - if (charlen > 0) { + for (i = 0; from[i] && i < maxwords; i++) { + charlen = codepage->uni2char(le16_to_cpu(from[i]), tmp, + NLS_MAX_CHARSET_SIZE); + if (charlen > 0) outlen += charlen; - } else { - to[outlen++] = '?'; + else + outlen++; + } + + return outlen; +} + +/* + * cifs_mapchar - convert a little-endian char to proper char in codepage + * @target - where converted character should be copied + * @src_char - 2 byte little-endian source character + * @cp - codepage to which character should be converted + * @mapchar - should character be mapped according to mapchars mount option? + * + * This function handles the conversion of a single character. It is the + * responsibility of the caller to ensure that the target buffer is large + * enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE). + */ +static int +cifs_mapchar(char *target, const __le16 src_char, const struct nls_table *cp, + bool mapchar) +{ + int len = 1; + + if (!mapchar) + goto cp_convert; + + /* + * BB: Cannot handle remapping UNI_SLASH until all the calls to + * build_path_from_dentry are modified, as they use slash as + * separator. + */ + switch (le16_to_cpu(src_char)) { + case UNI_COLON: + *target = ':'; + break; + case UNI_ASTERIK: + *target = '*'; + break; + case UNI_QUESTION: + *target = '?'; + break; + case UNI_PIPE: + *target = '|'; + break; + case UNI_GRTRTHAN: + *target = '>'; + break; + case UNI_LESSTHAN: + *target = '<'; + break; + default: + goto cp_convert; + } + +out: + return len; + +cp_convert: + len = cp->uni2char(le16_to_cpu(src_char), target, + NLS_MAX_CHARSET_SIZE); + if (len <= 0) { + *target = '?'; + len = 1; + } + goto out; +} + +/* + * cifs_from_ucs2 - convert utf16le string to local charset + * @to - destination buffer + * @from - source buffer + * @tolen - destination buffer size (in bytes) + * @fromlen - source buffer size (in bytes) + * @codepage - codepage to which characters should be converted + * @mapchar - should characters be remapped according to the mapchars option? + * + * Convert a little-endian ucs2le string (as sent by the server) to a string + * in the provided codepage. The tolen and fromlen parameters are to ensure + * that the code doesn't walk off of the end of the buffer (which is always + * a danger if the alignment of the source buffer is off). The destination + * string is always properly null terminated and fits in the destination + * buffer. Returns the length of the destination string in bytes (including + * null terminator). + * + * Note that some windows versions actually send multiword UTF-16 characters + * instead of straight UCS-2. The linux nls routines however aren't able to + * deal with those characters properly. In the event that we get some of + * those characters, they won't be translated properly. + */ +int +cifs_from_ucs2(char *to, const __le16 *from, int tolen, int fromlen, + const struct nls_table *codepage, bool mapchar) +{ + int i, charlen, safelen; + int outlen = 0; + int nullsize = nls_nullsize(codepage); + int fromwords = fromlen / 2; + char tmp[NLS_MAX_CHARSET_SIZE]; + + /* + * because the chars can be of varying widths, we need to take care + * not to overflow the destination buffer when we get close to the + * end of it. Until we get to this offset, we don't need to check + * for overflow however. + */ + safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize); + + for (i = 0; i < fromwords && from[i]; i++) { + /* + * check to see if converting this character might make the + * conversion bleed into the null terminator + */ + if (outlen >= safelen) { + charlen = cifs_mapchar(tmp, from[i], codepage, mapchar); + if ((outlen + charlen) > (tolen - nullsize)) + break; } + + /* put converted char into 'to' buffer */ + charlen = cifs_mapchar(&to[outlen], from[i], codepage, mapchar); + outlen += charlen; } - to[outlen] = 0; + + /* properly null-terminate string */ + for (i = 0; i < nullsize; i++) + to[outlen++] = 0; + return outlen; } @@ -88,3 +214,41 @@ cifs_strtoUCS(__le16 *to, const char *from, int len, return i; } +/* + * cifs_strndup_from_ucs - copy a string from wire format to the local codepage + * @src - source string + * @maxlen - don't walk past this many bytes in the source string + * @is_unicode - is this a unicode string? + * @codepage - destination codepage + * + * Take a string given by the server, convert it to the local codepage and + * put it in a new buffer. Returns a pointer to the new string or NULL on + * error. + */ +char * +cifs_strndup_from_ucs(const char *src, const int maxlen, const bool is_unicode, + const struct nls_table *codepage) +{ + int len; + char *dst; + + if (is_unicode) { + len = cifs_ucs2_bytes((__le16 *) src, maxlen, codepage); + len += nls_nullsize(codepage); + dst = kmalloc(len, GFP_KERNEL); + if (!dst) + return NULL; + cifs_from_ucs2(dst, (__le16 *) src, len, maxlen, codepage, + false); + } else { + len = strnlen(src, maxlen); + len++; + dst = kmalloc(len, GFP_KERNEL); + if (!dst) + return NULL; + strlcpy(dst, src, len); + } + + return dst; +} + |